Last active
November 24, 2020 22:02
-
-
Save piyush01123/0344ee8ccea32832f059fd7c436675d9 to your computer and use it in GitHub Desktop.
K Means clustering
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np, matplotlib.pyplot as plt | |
| def KMeans(X, K, num_steps=100): | |
| L = len(X) | |
| cluster_assignments=np.concatenate([np.full((L//K,), k) for k in range(K-1)]+[np.full((L-(K-1)*(L//K),), K-1)]) | |
| centroids = np.empty((K,*X.shape[1:])) | |
| for step in range(num_steps): | |
| # E step: centroid calculation | |
| for k in range(K): | |
| centroids[k] = X[cluster_assignments==k].mean(axis=0) | |
| # M step: cluster reassignment | |
| distances = np.array([[np.linalg.norm(x-c) for c in centroids] for x in X]) | |
| cluster_assignments = distances.argmin(axis=1) | |
| print("K=", K) | |
| print(cluster_assignments) | |
| plt.clf() | |
| for k in range(K): | |
| plt.scatter(X[cluster_assignments==k,0], X[cluster_assignments==k,1], label="C={}".format(k)) | |
| plt.legend() | |
| plt.savefig("kmeans_K_{}.jpg".format(K)) | |
| def main(): | |
| # {[−2,−1]T ,[−3,−2]T ,[0,−1]T ,[−1,0]T ,[2,3]T ,[−1,−2]T ,[3,2]T ,[3,3]T ,[1,1]T ,[2,2]T } | |
| X = np.array([[-2,-1], [-3,-2], [0,-1], [-1,0], [2,3], [-1,-2], [3,2], [3,3], \ | |
| [1,1], [2,2]]) | |
| KMeans(X, 2) | |
| KMeans(X, 3) | |
| KMeans(X, 4) | |
| KMeans(X, 5) | |
| KMeans(X, 6) | |
| KMeans(X, 8) | |
| KMeans(X, 9) | |
| KMeans(X, 10) | |
| main() |
Author
piyush01123
commented
Nov 24, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment